Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    text related to experiences, expertise, and skills in different areas and fields

    oai_token-act-pair · gpt-3.5-turbo

    statistical information related to experience and expertise in methods or techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fuckin
    -0.76
     alley
    -0.76
     unpop
    -0.76
     somew
    -0.75
     ,"
    -0.71
     Bulg
    -0.70
     subsequ
    -0.70
     Yun
    -0.70
     unsus
    -0.69
    ,)
    -0.69
    POSITIVE LOGITS
    âĢ¢
    2.96
     âĢ¢
    2.26
    âĢ¢âĢ¢
    1.84
    âĸº
    1.66
    ·
    1.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.59
    »
    1.53
     ·
    1.51
    âĻ¦
    1.47
    âĹı
    1.47
    Act Density 0.053%

    No Known Activations